ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Macaron V1 Tall vs Beam 1.0 501B A23B vs Solar Pro 4

No independent capability benchmark covers every model here yet. The score uses price, inputs & features and context window.

Price in rating: Included · Exclude price

  1. Mindlab

    Macaron V1 Tall

    Released Jul 21, 2026

    56/100
    • ECI—
    • Price$0.247 / $1.43
    • Context262K
  2. Reflection AI

    Beam 1.0 501B A23B

    Released Oct 5, 2026New

    52/100
    • ECI—
    • Price$0.40 / $1.20
    • Context1.05M
  3. Upstage

    Solar Pro 4

    Released Aug 6, 2026

    55/100
    • ECI—
    • Price$0.30 / $1.20
    • Context524K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Macaron V1 Tall 56/100, Solar Pro 4 55/100, Beam 1.0 501B A23B 52/100) compare the available specifications and price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

  • CapabilityNot enough dataNo independent benchmark covers every model here yet
  • Lowest priceSolar Pro 4Solar Pro 4 $0.525 · Macaron V1 Tall $0.543 · Beam 1.0 501B A23B $0.60 per 1M tokens (3:1 blend)
  • Longest contextBeam 1.0 501B A23BBeam 1.0 501B A23B 1,048,576 · Solar Pro 4 524,288 · Macaron V1 Tall 262,144 tokens
  • Widest inputsMacaron V1 TallMacaron V1 Tall: Text, Images · Beam 1.0 501B A23B: Text · Solar Pro 4: Text
  • Self-hostingMacaron V1 Tall and Beam 1.0 501B A23BPublishes downloadable weights (MIT and Apache-2.0)
How the score is built
MeasureWeightMacaron V1 TallBeam 1.0 501B A23BSolar Pro 4
Price50%605860
Inputs & features30%603545
Context window20%436554
Specs & price only100%56/10052/10055/100

Left out because at least one model lacks the data: capability. The remaining weights were rescaled.

02 — Side by side

Every spec in one table

Highlighted cells lead their row. Dashes mean the data is not published.

Macaron V1 Tall vs Beam 1.0 501B A23B vs Solar Pro 4 specifications side by side
SpecificationMacaron V1 TallMindlabBeam 1.0 501B A23BReflection AISolar Pro 4Upstage
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$0.247 (best)$0.40$0.30
Output$1.43$1.20 (best)$1.20 (best)
Cached input——$0.06
Blended (3:1)$0.543$0.60$0.525 (best)
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 1 providersMedian of 11 providersOfficial Upstage API
Limits
Context window262,144 tokens1,048,576 tokens (best)524,288 tokens
Max output32,768 tokens131,072 tokens (best)131,072 tokens (best)
Inputs and features
TextYesYesYes
ImagesYesNoNo
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningYesYesYesminimal · low · medium · high · xhigh · max
Tool callingYesYesYes
Structured outputNoNoYes
Availability
WeightsOpenMITOpenApache-2.0Proprietary
API model ID——solar-pro4
API providers117 (best)6
ReleasedJul 21, 2026Oct 5, 2026Aug 6, 2026
Knowledge cutoff—Jun 30, 2026Feb 2026
03 — Cost

What would a month cost?

Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.

  • Macaron V1 Tall$5.33
  • Beam 1.0 501B A23B$6.40
  • Solar Pro 4$5.40
04 — Questions

Which should you choose?

Which is better: Macaron V1 Tall, Beam 1.0 501B A23B or Solar Pro 4?

There is not enough shared capability evidence to name an overall winner. The scores (Macaron V1 Tall 56/100, Solar Pro 4 55/100, Beam 1.0 501B A23B 52/100) compare the available specifications and price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

Which is cheaper, Macaron V1 Tall, Beam 1.0 501B A23B or Solar Pro 4?

Solar Pro 4 is cheaper at $0.30 input / $1.20 output per million tokens (official Upstage API price). Macaron V1 Tall costs $0.247 input / $1.43 output per million tokens (median across 1 API provider); Beam 1.0 501B A23B costs $0.40 input / $1.20 output per million tokens (median across 11 API providers). At a typical mix of three input tokens to one output token, that is $0.525 per million tokens for Solar Pro 4 versus $0.543 for Macaron V1 Tall (1× as much) and $0.60 for Beam 1.0 501B A23B (1.1× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Macaron V1 Tall has not been scored yet, Beam 1.0 501B A23B has not been scored yet and Solar Pro 4 has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Macaron V1 Tall, Beam 1.0 501B A23B and Solar Pro 4 yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. All three support tool calling for agent workflows.

Which has the bigger context window?

Beam 1.0 501B A23B has the largest context window at 1,048,576 tokens, against 524,288 for Solar Pro 4 and 262,144 for Macaron V1 Tall. Maximum output per response: Macaron V1 Tall up to 32,768, Beam 1.0 501B A23B up to 131,072, Solar Pro 4 up to 131,072 tokens.

Which can read images, PDFs, audio or video?

Macaron V1 Tall accepts text and images; Beam 1.0 501B A23B accepts text; Solar Pro 4 accepts text. Macaron V1 Tall handles the widest range of inputs.

Are any of these open source?

Macaron V1 Tall and Beam 1.0 501B A23B publishes its weights (MIT and Apache-2.0) and can be self-hosted; Solar Pro 4 is proprietary.

Which is newer?

Beam 1.0 501B A23B is the newest, released Oct 5, 2026. Solar Pro 4 came out Aug 6, 2026; Macaron V1 Tall came out Jul 21, 2026. Knowledge cutoff: Beam 1.0 501B A23B Jun 30, 2026, Solar Pro 4 Feb 2026.

How do you decide the winner?

This rating uses price (50%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (30%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (20%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Nov 18, 2026.